GPolS: A Contextual Graph-Based Language Model for Analyzing Parliamentary Debates and Political Cohesion

Sawhney, Ravinder Singh; Wadhwa, Arnav; Agarwal, Shivam; Shah, Rajiv Ratn

doi:10.18653/v1/2020.coling-main.426

Cited by 7 publications

(5 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sentiment classification is one of the the most active areas of research in natural language processing. Within the domain of legislative debates, examples include classification of speeches from the US Congress (Burfoot et al, 2011;Ji and Smith, 2017;Proksch et al, 2019;Thomas et al, 2006), and the UK Parliament (Abercrombie and Batista-Navarro, 2018b, 2020; Bhavan et al, 2019;Salah, 2014;Sawhney et al, 2020). In these works-and in common with ours-speaker sentiment is assumed to be analogous to vote outcome.…”

Section: Related Workmentioning

confidence: 97%

Policy-focused Stance Detection in Parliamentary Debate Speeches

Abercrombie

Batista-Navarro

2022

NEJLT

View full text Add to dashboard Cite

Legislative debate transcripts provide citizens with information about the activities of their elected representatives, but are difficult for people to process. We propose the novel task of policy-focused stance detection, in which both the policy proposals under debate and the position of the speakers towards those proposals are identified. We adapt a previously existing dataset to include manual annotations of policy preferences, an established schema from political science. We evaluate a range of approaches to the automatic classification of policy preferences and speech sentiment polarity, including transformer-based text representations and a multi-task learning paradigm. We find that it is possible to identify the policies under discussion using features derived from the speeches, and that incorporating motion-dependent debate modelling, previously used to classify speech sentiment, also improves performance in the classification of policy preferences. We analyse the output of the best performing system, finding that discriminating features for the task are highly domain-specific, and that speeches that address policy preferences proposed by members of the same party can be among the most difficult to predict.

show abstract

Section: Related Workmentioning

confidence: 97%

Policy-focused Stance Detection in Parliamentary Debate Speeches

Abercrombie

Batista-Navarro

2022

NEJLT

View full text Add to dashboard Cite

show abstract

“…There is fascinating work that applies the idea of Graph Neural Networks for predicting the way that each member of a legislative branch will vote on an input motion (Sawhney et al, 2020). Our work does not try to predict how judges will vote based on any inputs, but instead generates debate cases given input arguments.…”

Section: Prior Workmentioning

confidence: 99%

Proceedings of the 4th New Frontiers in Summarization Workshop

2023

View full text Add to dashboard Cite

The development of intelligent systems capable of producing concise, fluent, and accurate summaries is a longstanding objective in natural language processing. This workshop serves as a forum for the exchange of ideas towards achieving this aim. It brings together experts from various disciplines, including summarization, language generation, and cognitive and psycholinguistics, to discuss key issues in automatic summarization. The agenda covers a wide array of topics, such as innovative paradigms and frameworks, multilingual and cross-lingual setups, shared tasks, information integration, novel evaluation methods, applied research, and future research directions. The workshop is aimed at fostering a cohesive research community, expediting the transfer of knowledge, and developing new tools, datasets, and resources to meet the needs of academia, industry, and government.

show abstract

“…Similarly, Defferrard et al, 2016;Peng et al, 2018;Henaff et al, 2015 use graph neural networks (GNNs) to represent a network of documents based on their references. Similar to our work but for a different problem and objective, Sawhney et al, 2020 analyze speech-level stance of members of the parliament, by performing node classification on graph attention networks (GATs), and Pujari and Goldwasser, 2021 analyze social media content generated by politicians using a graph transformer model.…”

Section: Related Workmentioning

confidence: 99%

Modeling U.S. State-Level Policies by Extracting Winners and Losers from Legislative Texts

Davoodi¹,

Waltenburg²,

Goldwasser³

2022

Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

Decisions on state-level policies have a deep effect on many aspects of our everyday life, such as health-care and education access. However, there is little understanding of how these policies and decisions are being formed in the legislative process. We take a datadriven approach by decoding the impact of legislation on relevant stakeholders (e.g., teachers in education bills) to understand legislators' decision-making process and votes. We build a new dataset for multiple US states that interconnects multiple sources of data including bills, stakeholders, legislators, and money donors. Next, we develop a textual graphbased model to embed and analyze state bills. Our model predicts winners/losers of bills and then utilizes them to better determine the legislative body's vote breakdown according to demographic/ideological criteria, e.g., gender.

show abstract

GPolS: A Contextual Graph-Based Language Model for Analyzing Parliamentary Debates and Political Cohesion

Cited by 7 publications

References 54 publications

Policy-focused Stance Detection in Parliamentary Debate Speeches

Policy-focused Stance Detection in Parliamentary Debate Speeches

Proceedings of the 4th New Frontiers in Summarization Workshop

Modeling U.S. State-Level Policies by Extracting Winners and Losers from Legislative Texts

Contact Info

Product

Resources

About